{"id":"https://openalex.org/W4408352873","doi":"https://doi.org/10.1109/icassp49660.2025.10887663","title":"An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation","display_name":"An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352873","doi":"https://doi.org/10.1109/icassp49660.2025.10887663"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102596593","display_name":"Yuxuan Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Dong","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102560553","display_name":"Hengyi Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyi Hong","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038529708","display_name":"Ya Jiang","orcid":"https://orcid.org/0000-0003-1733-8887"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Jiang","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060276344","display_name":"Shi Cheng","orcid":"https://orcid.org/0000-0002-7341-3135"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Cheng","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":5.0693,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.95120105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6953333616256714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6827036738395691},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6049494743347168},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.596426248550415},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4717826545238495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4065057635307312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3935388922691345},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.28532177209854126},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1321411430835724}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6953333616256714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6827036738395691},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6049494743347168},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.596426248550415},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4717826545238495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065057635307312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3935388922691345},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28532177209854126},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1321411430835724},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2113638573","https://openalex.org/W2123843894","https://openalex.org/W2128131274","https://openalex.org/W2135131618","https://openalex.org/W2292996718","https://openalex.org/W2746554716","https://openalex.org/W2810934215","https://openalex.org/W2936774411","https://openalex.org/W2964342924","https://openalex.org/W2998139081","https://openalex.org/W3163193264","https://openalex.org/W3206329344","https://openalex.org/W4205689591","https://openalex.org/W4221141618","https://openalex.org/W4324116353","https://openalex.org/W4372263497","https://openalex.org/W4375868779","https://openalex.org/W4386764032","https://openalex.org/W4390096820","https://openalex.org/W4392903703","https://openalex.org/W4392903899","https://openalex.org/W4392904420","https://openalex.org/W4402979486","https://openalex.org/W4404577061","https://openalex.org/W6631190155","https://openalex.org/W6684354967","https://openalex.org/W6779923105","https://openalex.org/W6784117923","https://openalex.org/W6853532597","https://openalex.org/W6869931805"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W1996130883","https://openalex.org/W611303608","https://openalex.org/W2748574964","https://openalex.org/W4313595395"],"abstract_inverted_index":{"In":[0],"traditional":[1],"sound":[2,14,33],"event":[3,15],"localization":[4],"and":[5,18,67,74,80,99,102,111],"detection":[6,16],"(SELD)":[7],"tasks,":[8],"the":[9,32,123,130,137],"focus":[10],"is":[11,144],"typically":[12],"on":[13,147],"(SED)":[17],"direction-of-arrival":[19],"(DOA)":[20],"estimation,":[21],"but":[22],"they":[23],"fall":[24],"short":[25],"of":[26,132],"providing":[27],"full":[28],"spatial":[29,51],"information":[30],"about":[31],"source.":[34],"The":[35,141],"3D":[36,86,138],"SELD":[37,139],"task":[38],"addresses":[39],"this":[40,59],"limitation":[41],"by":[42],"integrating":[43],"source":[44,92],"distance":[45,75,100],"estimation":[46,76],"(SDE),":[47],"allowing":[48],"for":[49,96,135],"complete":[50],"localization.":[52],"We":[53],"propose":[54],"three":[55],"approaches":[56],"to":[57,84],"tackle":[58],"challenge:":[60],"a":[61,88,103,114],"novel":[62],"method":[63,119],"with":[64,91],"independent":[65],"training":[66],"joint":[68,133],"prediction,":[69],"which":[70],"firstly":[71],"treats":[72],"DOA":[73,98],"as":[77],"separate":[78],"tasks":[79],"then":[81],"combines":[82],"them":[83],"solve":[85],"SELD;":[87],"dual-branch":[89],"representation":[90],"Cartesian":[93],"coordinate":[94],"used":[95],"simultaneous":[97],"estimation;":[101],"three-branch":[104],"structure":[105],"that":[106],"jointly":[107],"models":[108],"SED,":[109],"DOA,":[110],"SDE":[112],"within":[113],"unified":[115],"framework.":[116],"Our":[117],"proposed":[118],"ranked":[120],"first":[121],"in":[122],"DCASE":[124],"2024":[125],"Challenge":[126],"Task":[127],"3,":[128],"demonstrating":[129],"effectiveness":[131],"modeling":[134],"addressing":[136],"task.":[140],"relevant":[142],"code":[143],"available":[145],"now":[146],"https://github.com/yxdong0320/Solution_on_3D_SELD.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
